- DATA
- MAPS
- LISTS
- HUMAN
Short answer
How can I find specific landmarks or infrastructure with my AI?
Your AI uses the Overpass MCP to translate your descriptions into structured JSON data. This allows you to pinpoint exact locations, such as hospitals, parks, or power lines, within any area you define. You'll get precise geographic data ready for your next task.
The results you get.
Where your data lands.
The AI processes your request and organizes the results into these formats.
DATA
Structured JSON output
The AI converts your request into a clean JSON object. This makes the geographic data easy to use in other apps or scripts.
MAPS
Geographic coordinates
You get the exact latitude and longitude for every landmark found. This allows you to plot points on any map interface.
LISTS
Filtered property lists
The AI extracts specific attributes for the items it finds. You'll see names, types, and other relevant metadata for each point of interest.
HUMAN
Manual verification
You review the final list to ensure the AI captured the exact infrastructure or landmarks you intended to find.
The workflow
What your AI does when a request arrives.
The AI handles the heavy lifting of translating human intent into geographic queries.
Interpret intent
Your agent reads your natural language request to understand what kind of landmark or infrastructure you are looking for.
execute_queryBuild the query
The AI constructs the specific logic needed to search the OpenStreetMap database for your target area.
execute_queryFetch data
The agent runs the query to pull raw geographic information from the Overpass API.
execute_queryFormat results
The AI cleans up the raw data and presents it as a structured, readable list or JSON object.
execute_query
Try it
Copy these to start.
Use these prompts to begin your search.
Starting points
Replace the bracketed text with your specific location and the type of landmark you want to find.
Overpass API Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_zzdgleuR8jSsqRIakxavJFmaXkwVJPywGnPhOsDn/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Overpass API capabilities are ready to use.
{
"mcpServers": {
"overpass-mcp": {
"url": "https://edge.vinkius.com/vk_preview_zzdgleuR8jSsqRIakxavJFmaXkwVJPywGnPhOsDn/mcp"
}
}
}Find all the hospitals within 5 kilometers of [London Eye].
Locate every subway station in [Brooklyn, NY] and give me the coordinates.
List all the public parks in [Berlin] that have a playground.
Find the locations of all electrical substations in [Austin, Texas].
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Overpass once, then ask.
One click connects the MCP to your client. Your credentials stay encrypted, and you can start querying immediately.
Connect Overpass to your AIFAQ
How this task behaves.
- 01
Can the AI update or delete landmarks in the database?
No. The AI can only read and retrieve existing data through the execute_query tool.
- 02
Does the AI create its own maps?
No. The AI provides the raw data and coordinates, which you can then use in your own mapping software.
- 03
Can I search for things outside of a specific area?
The AI requires a defined area or a reference point to perform a query effectively.
- 04
What kind of data can I find?
You can find almost any infrastructure or landmark that is mapped in OpenStreetMap, such as roads, buildings, or utilities.
- 05
Will the AI automatically save these points to a file?
No. The AI provides the data in the chat interface, and you decide how to save or export it.
More questions about Overpass? The Connector page answers them. See everything the Overpass Connector can do
Connect Overpass API to Claude, Cursor, ChatGPT & more
